Classification of road curves and corresponding driving profile via smartphone trip data

Smart cities are the new settlement structures formed by new technologies that change human life. Among these technologies, intelligent automobiles have an important place, and many scientific studies on it have been realized. Especially Tesla, Apple, and Google have completed their prototypes of autonomous automobiles. One of the indispensable part of recent automotive technologies is Advanced Driver Assistance System (ADAS). This system has been developed to improve safety and comfort of driver while driving. In this study, we have tried to predict road geometry and driving profile by using sensor data acquired by driver smartphone on steering wheel for a certain trip. Driving profiles are identified as aggressive and safe. GPS, accelerometer and gyroscope sensors are employed in this study. Using smartphone sensor data, road portions are initially determined by the proposed algorithm. Then, road shapes are obtained by a Fuzzy Classifier, which are straight, right curved, and left curved. Afterwards, the acceleration data corresponding road shapes are considered to find acceleration type for the portion of that road. Transitions between straight and curved roads including vehicle speed are determined by Hidden Markov Model (HMM). Thus, speed preference of subject driver for corresponding road shapes are obtained in probabilistic manner. Validation results have shown that the error rate between ground truth and observation data for proposed approach is obtained as 11.81%. Consequently, driving profile have been estimated considering road shapes.